DeepSeek V3.1
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 164 K tokens
- Max output
- 33 K
- Input, $ per 1M tokens
- $0.250
- Output, $ per 1M tokens
- $0.950
- Cache read, $ per 1M
- $0.130
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 08/21/2025
- Knowledge cutoff
- —
- API id
- deepseek/deepseek-chat-v3.1
Summary from the data
DeepSeek V3.1 is a DeepSeek model available by API since 08/21/2025. It costs $0.250 per million input tokens and $0.950 per million output tokens, accepts 164 K tokens of context and generates up to 33 K tokens per response. Input: text; output: text. It has a reasoning mode. It supports tool calling. With 10,000 requests a month of 1,500 input and 400 output tokens it would cost about $7.55 a month.
Compare DeepSeek V3.1 with…
- DeepSeek V3.1 vs DeepSeek V4.1 Flash
- DeepSeek V3.1 vs DeepSeek V4 Flash Vision Exp
- DeepSeek V3.1 vs DeepSeek V4 Pro 0813
- DeepSeek V3.1 vs DeepSeek V4 Flash 0731
- DeepSeek V3.1 vs Claude Sonnet 5.5
- DeepSeek V3.1 vs Gemini 3.8 Flash
- DeepSeek V3.1 vs Mistral Medium 3.5
- DeepSeek V3.1 vs Kimi K3
- DeepSeek V3.1 vs GPT-6.1 Sol
- DeepSeek V3.1 vs Qwen3.8 Max Prime
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4 Flash 0731 DeepSeek$1.55
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Frequently asked questions
How much does DeepSeek V3.1 cost per million tokens?
DeepSeek V3.1 costs $0.250 per million input tokens and $0.950 per million output tokens (USD, list price). Cache read: $0.130. Batch tier: not published.
What context window does DeepSeek V3.1 have?
DeepSeek V3.1 accepts 164 K tokens of context per request and generates up to 33 K tokens per response.
Does DeepSeek V3.1 accept images, audio or files?
Input: text. Output: text.
Does DeepSeek V3.1 have a reasoning mode and tool calling?
It has a reasoning mode. It supports tool calling.
When was DeepSeek V3.1 released and what is its knowledge cutoff?
DeepSeek V3.1 has been available by API since 08/21/2025. Knowledge cutoff: not published.
What would an app built on DeepSeek V3.1 cost?
With 10,000 requests a month of 1,500 input and 400 output tokens, DeepSeek V3.1 would cost about $7.55 a month at list price, without cache or batch discounts.
What is the API id of DeepSeek V3.1?
The id is deepseek/deepseek-chat-v3.1. It is the name passed in the model parameter of the API (or on OpenRouter).
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.